Thumbs-down a Claude Code mistake once, and ThumbGate warns the next time it tries that command. After three thumbs-downs on the same command, strict mode blocks it.
Run Claude Code with bypass permissions and ThumbGate checks every call: secret leaks and catastrophic commands are denied, other flagged actions warn, strict mode blocks them.
Who it's for: Claude Code users whose agent has already broken something once. The local CLI is free.
THUMBGATE_STRICT_ENFORCEMENT=1: three thumbs-downs, then the fourth attempt is denied. A reworded delete is not caught. How it was recorded.$ echo '{"tool_name":"Bash","tool_input":{"command":"git push --force origin main"}}' | thumbgate gate-check
{"hookSpecificOutput":{"hookEventName":"PreToolUse","permissionDecision":"deny",
"permissionDecisionReason":"[GATE:force-push] Force push blocked. This is destructive and irreversible."}}
$ ... "git reset --hard HEAD~5"
"permissionDecisionReason":"[GATE:git-reset-hard] git reset --hard is blocked because it can destroy uncommitted work. Stash or use a non-destructive restore path ..."
$ ... "rm -rf ~/"
"permissionDecisionReason":"[GATE:rm-rf-home-or-root] Broad rm -rf against root or home is blocked. Use a narrow, reviewed path ..."
Recorded from thumbgate gate-check v1.40.3. Claude reads the permissionDecisionReason and changes course. These three deny by default. Hard deny for every other flagged action is strict mode, one env var: THUMBGATE_STRICT_ENFORCEMENT=1.
1 · Install the plugin inside Claude Code
/plugin marketplace add IgorGanapolsky/ThumbGate
/plugin install thumbgate@thumbgate-marketplace
2 · Set up the status line in your terminal, no manual config
npx thumbgate init --agent claude
Step 2 writes the hooks and the status line into your Claude Code settings. Restart Claude Code and the line below appears.
main · ThumbGate v1.40.3 · Pro · 0👍 2👎 this project · Dashboard · Latest success 11/16/2026 18:00:28: Accurate
- 0👍 2👎 this project Live count of the thumbs you gave in the project you are in. Automated and imported feedback is not counted.
- Dashboard One click opens your local dashboard.
- Latest success … The most recent lesson ThumbGate captured.
Catch it. Signal it. Enforce it.
- 1 · Catch Claude tries something you rejected before, like
npm publishfrom the wrong branch, or mocking the database in an end-to-end test. - 2 · Signal One thumbs-down with the reason:
npx thumbgate capture --feedback=down --context="mocked the DB in an e2e test" - 3 · Enforce A local PreToolUse gate checks every future tool call in every Claude Code session in that project. A match warns Claude with your reason; in strict mode, after three thumbs-downs, it is denied.
What init adds to your Claude Code settings
{
"statusLine": { "type": "command", "command": "node \"<path to thumbgate>/bin/cli.js\" statusline-render" },
"hooks": {
"PreToolUse": [
{ "matcher": ".*",
"hooks": [ { "type": "command", "command": "node \"<path to thumbgate>/bin/cli.js\" gate-check" } ] }
]
}
}
Written by npx thumbgate init --agent claude into a fresh Claude Code home; the path points at the installed package. They are ordinary Claude Code hooks, so they show up in /hooks.
Your own hooks vs ThumbGate.
| Own hooks + deny rules | ThumbGate | |
|---|---|---|
| Where a rule comes from | You write the pattern by hand | One thumbs-down with a reason becomes a warning rule |
| Across sessions | Whatever you saved in settings | Learned rules live on disk and load every session |
| What Claude is told | Whatever message you wrote | Your own reason is shown to Claude in the warning |
Visible in /hooks | Yes | Yes |
A firewall for AI coding agents, built for Claude Code. Other agents are listed under Also works with.
Dashboard: npx thumbgate dashboard --open · /thumbgate-dashboard · thumbgate-dashboard · demo · strict-mode deny example ↓
Why Pro is worth $__PRO_PRICE_DOLLARS__
Free blocks force-push, git reset --hard, git clean -f, rm -rf on home or root and DROP TABLE by default. Pro is about memory.
- Every learned rule stays active. Free keeps your first 3 learned rules active. Pro keeps all of them.
- Recall. Ask what Claude got wrong before, and search past lessons. Both are Pro only.
- Coming, not shipped yet: team-shared rules, lessons synced across machines, audit history.
Thumbs teach. The gate enforces.
Pre-action checks—and the systems that refine them.
Corrections become local lessons; repeated negatives become gates; the next action is checked before execution. Click a step for the under-the-hood demo.
Capture feedback
Record explicit 👍 or 👎 with the action and outcome context.
Under the hood ↓Remember locally
Store a reviewable lesson that survives sessions without writing into model weights.
Under the hood ↓Rank and refine
Re-rank lessons for the action. Repeated negatives become gates that warn, or block in strict mode; stale gates expire.
Under the hood ↓Gate the next action
The action is allowed, warned, or denied before the tool proceeds.
Capture feedback
Each reviewed outcome closes the loop—under your control. Lessons are re-ranked per action, repeated failures can promote into gates, and stale auto-promoted gates expire. The firewall improves from explicit feedback without retraining the model or silently rewriting policy.
Hard deny where configured. Honest warning everywhere else.
proposed git push --force origin main mode strict enforcement rule protect-main source core protection · strict mode decision DENY reason force-push to protected branch next decision recorded before execution
Why not a static hook? Prompts compact away; static bash hooks don't learn from 👍/👎. Detected secret exfiltration and gate-process bypass attempts are denied by default. Catastrophic commands (force-push, reset --hard, rm -rf on home or root, DROP TABLE) are denied by default. Other matching destructive actions warn by default and deny in strict mode. This is a managed strict-mode example, not a claim that every free install blocks every risky command automatically.
Five questions, answered plainly.
Get warned before your agent repeats last week's mistake.
Run npx thumbgate init (MIT), or choose self-serve Pro.
ThumbGate also installs for Cursor, Codex, Gemini CLI, Cline, OpenCode, Amp, Grok and Hermes. Claude Code is the first-class path.
Enforcement by agent and mode
| Agent | Enforcement | Default (secrets) | Default (destructive) | Strict mode |
|---|---|---|---|---|
| Claude Code | Blocks before tool runs | DENY | DENY catastrophic, WARN other | DENY |
| Cursor, Cline, OpenCode | Advisory | DENY | WARN | DENY |
| Amp | Feedback only | Logged | Logged | Logged |